mirror of
https://ghfast.top/https://github.com/aeroxw/tick-stock-panel.git
synced 2026-09-12 17:54:15 +08:00
shy3130
e0cd625ef4
- 因子平台: /factors 一级页(检验/因子库/编辑器/组合/挖掘), DSL 公式因子(25 算子点选、双语字段、我的因子模板、脏公式守卫), 版本与生命周期, 自动挖掘 L1 统计筛选 - 因子↔策略四条桥: 触发器 Zap 快建因子条件信号、因子一键生成排名策略、自定义信号 AI 提示词接入因子分组、策略回测因子归因(胜/败单入场信号日因子均值, 独立 tab, 双语因子名) - 回测: 统计卡新增盈亏比(≥1 红/<1 绿), 蒙卡回撤合并为中位/95% 双值卡(自适应字号), 高级设置基础过滤与策略编辑器参数对齐(5 组区间) - 信号库独立页 /signals(原设置 tab 迁出), 持仓提醒入导航; 挖掘并入因子页第 5 tab, /mining 旧链接重定向 - 研究线配套: 因子目录 61→77(评分/矩阵双内核), stats_v2(Newey-West/BH-FDR/DSR), enriched 管道与异动/报价服务配套调整 - 文档: README 导航与特性表、features.md 因子平台章节、操作说明书 9.2、factor-platform-plan 执行状态与 §5、二开文档桥接说明; 交流与支持节改版 - 版本 0.2.2 → 0.2.3; 后端全量 1625 passed(1 例环境性跳过), 前端 build 通过
84 lines
3.8 KiB
Python
84 lines
3.8 KiB
Python
"""收盘价过期分区回归: 盘后管道必须重算"行数完整但价格停留在竞价前"的 enriched 分区。
|
|
|
|
实时 flush 可能在收盘集合竞价结果发布前写入当日分区 (实测 2026-09-04: TickFlow
|
|
实时端点收盘后仍返回旧价, 3392/5554 只股票 enriched 收盘价与官方日线不符),
|
|
分区行数与 daily 相同, #223 的行数校验识别不到, 增量路径不会重算, 当日偏离值/
|
|
动量等全部 enriched 消费方都会用旧价 (海鸥住工 10 日偏离 98.77% vs 官方 99.61%)。
|
|
_prune_stale_price_partitions 按官方日线做 raw_close vs close 值级比对, 不一致即
|
|
删分区, 让增量重算按官方日线全市场重建。
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import polars as pl
|
|
|
|
from app.jobs.daily_pipeline import _prune_stale_price_partitions
|
|
|
|
|
|
def _write_partition(base: Path, day: str, symbols: list[str], closes: list[float], col: str) -> None:
|
|
part = base / f"date={day}"
|
|
part.mkdir(parents=True, exist_ok=True)
|
|
pl.DataFrame({"symbol": symbols, col: closes}).write_parquet(part / "part.parquet")
|
|
|
|
|
|
def test_stale_close_partition_is_pruned(tmp_path) -> None:
|
|
daily = tmp_path / "kline_daily"
|
|
enriched = tmp_path / "kline_daily_enriched"
|
|
syms = ["002084.SZ", "600519.SH", "000001.SZ"]
|
|
# 2026-09-04: 官方日线收盘 7.10, 实时写入的 enriched 停留在竞价前 7.07;
|
|
# 行数两侧一致 (覆盖全), #223 行数校验识别不到 (issue 实测形态)
|
|
_write_partition(daily, "2026-09-04", syms, [7.10, 1330.10, 11.89], "close")
|
|
_write_partition(enriched, "2026-09-04", syms, [7.07, 1330.10, 11.89], "raw_close")
|
|
|
|
pruned = _prune_stale_price_partitions(daily, enriched)
|
|
|
|
assert pruned == ["2026-09-04"]
|
|
assert not (enriched / "date=2026-09-04").exists()
|
|
|
|
|
|
def test_matching_close_partitions_untouched(tmp_path) -> None:
|
|
daily = tmp_path / "kline_daily"
|
|
enriched = tmp_path / "kline_daily_enriched"
|
|
syms = ["002084.SZ", "600519.SH"]
|
|
_write_partition(daily, "2026-09-04", syms, [7.10, 1330.10], "close")
|
|
_write_partition(enriched, "2026-09-04", syms, [7.10, 1330.10], "raw_close")
|
|
|
|
assert _prune_stale_price_partitions(daily, enriched) == []
|
|
assert (enriched / "date=2026-09-04" / "part.parquet").exists()
|
|
|
|
|
|
def test_multiple_stale_dates_all_pruned(tmp_path) -> None:
|
|
# 管道连续数日未触发重建时, 最近多个交易日的过期分区一并修复
|
|
daily = tmp_path / "kline_daily"
|
|
enriched = tmp_path / "kline_daily_enriched"
|
|
for day, stale in [("2026-09-04", 7.07), ("2026-09-03", 6.88), ("2026-09-02", 6.80)]:
|
|
_write_partition(daily, day, ["002084.SZ"], [stale + 0.03], "close")
|
|
_write_partition(enriched, day, ["002084.SZ"], [stale], "raw_close")
|
|
|
|
pruned = _prune_stale_price_partitions(daily, enriched)
|
|
|
|
assert sorted(pruned) == ["2026-09-02", "2026-09-03", "2026-09-04"]
|
|
|
|
|
|
def test_missing_raw_close_column_left_alone(tmp_path) -> None:
|
|
# 旧 schema 无 raw_close 列 → 读列失败, 交给既有完整性检查, 不误删
|
|
daily = tmp_path / "kline_daily"
|
|
enriched = tmp_path / "kline_daily_enriched"
|
|
_write_partition(daily, "2026-09-04", ["002084.SZ"], [7.10], "close")
|
|
part = enriched / "date=2026-09-04"
|
|
part.mkdir(parents=True)
|
|
pl.DataFrame({"symbol": ["002084.SZ"], "close": [7.07]}).write_parquet(part / "part.parquet")
|
|
|
|
assert _prune_stale_price_partitions(daily, enriched) == []
|
|
assert (part / "part.parquet").exists()
|
|
|
|
|
|
def test_daily_partition_missing_left_alone(tmp_path) -> None:
|
|
# 官方日线尚未同步的日期不比对 (留给当日正常流程)
|
|
enriched = tmp_path / "kline_daily_enriched"
|
|
_write_partition(enriched, "2026-09-04", ["002084.SZ"], [7.07], "raw_close")
|
|
|
|
assert _prune_stale_price_partitions(tmp_path / "kline_daily", enriched) == []
|
|
assert (enriched / "date=2026-09-04" / "part.parquet").exists()
|